Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strings
    0.96
     diagonals
    0.94
     vouchers
    0.94
     strlen
    0.93
     phenols
    0.90
     data
    0.88
     lbs
    0.87
     fentanyl
    0.87
     qubits
    0.87
     diethyl
    0.87
    POSITIVE LOGITS
    Abstract
    1.31
     Custom
    1.12
     Abstract
    1.12
    Concrete
    1.10
     Concrete
    1.08
    Custom
    1.07
    Reusable
    1.05
    Conversation
    0.99
    Composite
    0.98
    Person
    0.97
    Act Density 0.411%

    No Known Activations